Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3007 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9117. Min Range: -3.9117
Max Act: 3.9117. Min Act: -0.1700
Data Index: 581190 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9117. Min Range: -3.9117
Max Act: 3.8492. Min Act: -0.1700
Data Index: 3530790 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9117. Min Range: -3.9117
Max Act: 3.8492. Min Act: -0.1700
Data Index: 758495 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9117. Min Range: -3.9117
Max Act: 3.8179. Min Act: -0.1700
Data Index: 2060371 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9117. Min Range: -3.9117
Max Act: 3.8179. Min Act: -0.1700
Data Index: 3368195 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9117. Min Range: -3.9117
Max Act: 3.7866. Min Act: -0.1700
Data Index: 6059429 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9117. Min Range: -3.9117
Max Act: 3.7866. Min Act: -0.1700
Data Index: 7408005 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9117. Min Range: -3.9117
Max Act: 3.7866. Min Act: -0.1700
Data Index: 5402064 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9117. Min Range: -3.9117
Max Act: 3.7866. Min Act: -0.1700
Data Index: 2378870 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9117. Min Range: -3.9117
Max Act: 3.7866. Min Act: -0.1700
Data Index: 27741 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9117. Min Range: -3.9117
Max Act: 3.7553. Min Act: -0.1700
Data Index: 5138283 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9117. Min Range: -3.9117
Max Act: 3.7553. Min Act: -0.1700
Data Index: 585074 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9117. Min Range: -3.9117
Max Act: 3.7553. Min Act: -0.1700
Data Index: 8042762 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9117. Min Range: -3.9117
Max Act: 3.7553. Min Act: -0.1700
Data Index: 1715575 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9117. Min Range: -3.9117
Max Act: 3.7241. Min Act: -0.1700
Data Index: 5023018 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9117. Min Range: -3.9117
Max Act: 3.7241. Min Act: -0.1700
Data Index: 1362704 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9117. Min Range: -3.9117
Max Act: 3.7241. Min Act: -0.1700
Data Index: 7112207 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9117. Min Range: -3.9117
Max Act: 3.7241. Min Act: -0.1700
Data Index: 3270411 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9117. Min Range: -3.9117
Max Act: 3.7241. Min Act: -0.1700
Data Index: 6417833 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9117. Min Range: -3.9117
Max Act: 3.7241. Min Act: -0.1700
Data Index: 7092630 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19